Segmentation fault (core dumped) - while using Chroma from langchain_chroma

[Yash2003Bisht]

Checked other resources

• I added a very descriptive title to this issue.
• I searched the LangChain documentation with the integrated search.
• I used the GitHub search to find a similar question and didn't find it.
• I am sure that this is a bug in LangChain rather than my code.
• The bug is not resolved by updating to the latest stable version of LangChain (or the specific integration package).

Example Code

def find_similar_pages(self, query: str, website_id: int, 
                          num_results: int = 5) -> List[Dict[str, Any]]:
        """
        Find similar pages for a given query within a specific website.
        Returns pages with similarity scores >= 0.4
        """
        try:
            results = self.vectorstore.similarity_search_with_relevance_scores(
                query,
                k=num_results,
                score_threshold=0.4,
                filter={"website_id": website_id},
            )

            similar_pages = []
            for doc, similarity_score in results:
                metadata = doc.metadata
                similar_pages.append({
                    "url": metadata["url"],
                    "title": metadata["title"],
                    "summary": doc.page_content.split("\n\n")[1],
                    "query": query,
                    "similarity": round(similarity_score, 3)
                })
            
            logger.debug(f"Found {len(similar_pages)} similar pages for website_id {website_id}")
            return similar_pages
            
        except Exception as e:
            logger.error(f"Error querying ChromaDB for website_id {website_id}: {str(e)}", exc_info=True)
            return []

Error Message and Stack Trace (if applicable)

Description

While performing the similarity search with relevance score i get Segmentation fault (core dumped). I'm using HuggingFaceInferenceAPIEmbeddings to embed documents using sentence-transformers/all-MiniLM-L6-v2

System Info

System Information

OS: Linux
OS Version: #1 SMP PREEMPT_DYNAMIC Debian 6.1.128-1 (2025-02-07)
Python Version: 3.11.11 (main, Mar 17 2025, 23:23:20) [GCC 12.2.0]

Package Information

langchain_core: 0.3.30
langchain: 0.3.14
langchain_community: 0.3.14
langsmith: 0.2.11
langchain_chroma: 0.2.0
langchain_openai: 0.3.0
langchain_text_splitters: 0.3.5

Optional packages not installed

langserve

Other Dependencies

aiohttp: 3.8.4
async-timeout: 4.0.2
chromadb: 0.5.20
dataclasses-json: 0.6.1
fastapi: 0.115.6
httpx: 0.28.1
httpx-sse: 0.4.0
jsonpatch: 1.33
langsmith-pyo3: Installed. No version info available.
numpy: 1.26.1
openai: 1.59.8
orjson: 3.10.14
packaging: 23.2
pydantic: 2.10.5
pydantic-settings: 2.7.1
PyYAML: 6.0
requests: 2.31.0
requests-toolbelt: 1.0.0
SQLAlchemy: 2.0.22
tenacity: 8.2.3
tiktoken: 0.8.0
typing-extensions: 4.12.2
zstandard: Installed. No version info available.

[DvGils]

I had a very similar issue using DuckDB. It was fixed when i installed pandas. Might work for you as well. See #29933 (and related PRs #30435 & #30445)